C++ Engineer (Computer Vision)

Location: Gurugram | Work Mode: Work From Office

Make Computer Vision run faster, smarter, and at scale.

Awiros is a Series A-funded deep-tech company (~$7M raised) building the world’s first app-based Operating System for Computer Vision.

Founded in 2015, our platform enables developers and enterprises to build, deploy, and scale AI-powered video applications across edge and cloud environments.

We work at the intersection of Computer Vision, Deep Learning, C++, GPU computing, and distributed systems, building technology that processes real-time video and high-throughput workloads in real-world deployments.

At Awiros, Computer Vision isn’t just about building a model that works. It’s about making that intelligence fast, efficient, reliable, and production-ready.

THE ROLE:

We’re looking for a C++ Computer Vision Engineer to build and optimize the systems that bring Computer Vision algorithms into production.

You’ll work at the intersection of Computer Vision algorithms and high-performance software engineering - implementing vision pipelines, integrating AI models, optimizing inference, and building efficient components for real-time video analytics.

You’ll work closely with our Computer Vision, AI, Platform, and Systems teams to take solutions from algorithm to deployment, with a strong focus on performance, reliability, and real-world constraints.

WHAT YOU'LL WORK ON:

• •Design and develop high-performance Computer Vision components and video processing pipelines in C++.
• •Implement and optimize algorithms for object detection, tracking, recognition, segmentation, image processing, and other video analytics use cases.
• •Integrate Deep Learning models into production inference pipelines.
• •Optimize AI/CV workloads for latency, throughput, memory utilization, and compute efficiency.
• •Work with GPU-accelerated inference and frameworks such as TensorRT, CUDA, or similar technologies.
• •Profile applications, identify bottlenecks, and improve system-level performance.
• •Work with model artifacts such as ONNX and integrate them into C++ inference pipelines.
• •Build robust solutions for real-time video processing and large-scale deployments.
• •Debug issues across the algorithm, application, inference, and hardware layers.
• •Collaborate with Computer Vision and Platform engineers to integrate CV components into the broader Awiros ecosystem.
• •Take ownership of features from implementation → optimization → integration → deployment.

WHAT YOU BRING:

Must Have

• •Strong programming skills in C++.
• •Strong understanding of Data Structures, Algorithms, and Object-Oriented Programming.
• •Solid understanding of Computer Vision fundamentals.
• •Hands-on experience with OpenCV or similar Computer Vision libraries.
• •Understanding of image and video processing concepts such as image transformations, filtering, feature extraction, detection, tracking, and segmentation.
• •Strong debugging and problem-solving skills.
• •Experience developing production-quality software, not just academic implementations.

Good to Have

• •Experience with CUDA and GPU programming.
• •Experience with TensorRT, ONNX Runtime, OpenVINO, or similar inference frameworks.
• •Experience working with ONNX model integration and optimization.
• •Understanding of Deep Learning models and inference pipelines.
• •Experience with multi-threading, concurrency, or parallel programming in C++.
• •Exposure to Linux-based development and performance profiling.
• •Familiarity with technologies such as Docker, Kubernetes, Kafka, or distributed systems.
• •Experience working with real-time video or edge computing.

WHY AWIROS?

Work on Computer Vision in the real world

Build software that processes real-time video on real deployments, where latency, reliability, and performance matter.

Go deep into C++ and systems

Work across C++, GPU computing, inference optimization, video processing, and distributed systems.

Solve performance-critical problems

Work on challenges involving high-throughput video, constrained compute, inference latency, and large-scale deployments.

Own the complete journey

See your work move from algorithm → implementation → optimization → integration → production.

Build the infrastructure behind AI

Your work will help turn Computer Vision models and algorithms into reliable, scalable video intelligence applications.

If you enjoy writing high-performance C++ and want to solve the engineering challenges behind real-time Computer Vision, we’d like to hear from you.